How to Use the Ebby MCP in Pydantic AI

Q: How do I initialize the Ebby MCP Server inside Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint, and pass it to the toolsets argument of your Pydantic AI Agent. Do not use the deprecated MCPServerHTTP class when configuring Ebby.

Q: Can my Pydantic AI agent track pending Ebby uploads safely?

Yes, your Pydantic AI agent calls listinprogresstranscriptions to monitor the queue. The Pydantic AI framework validates the status fields against your models, ensuring your loop only proceeds when the Ebby data is clean.

Q: How do I handle successfully processed Ebby audio files in Pydantic AI?

Have your Pydantic AI agent call listsuccessfullyprocessedaudio to find files ready for export. The returned list of Ebby files is parsed directly into typed Python objects for safe Pydantic AI downstream processing.

Build type-safe Pydantic AI agents that validate Ebby audio transcriptions and speaker metadata at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ebby MCP to Pydantic AI

Create your Vinkius account to connect Ebby to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Ebby with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate transcription metadata with Pydantic AI

Your Pydantic AI agent uses `get_ebby_account_metadata` to retrieve your account usage and limits. Because Pydantic AI enforces strict type safety, the returned fields are parsed against your schema at runtime, catching any unexpected data formats immediately. If you need to search Ebby files, the Pydantic AI agent calls `search_transcriptions_by_name` using strict string filters. This ensures your search queries match your model's expected input structure before making the API call.

Enforce schema validation on this MCP Server

This MCP Server integrates with your Pydantic AI agent to guarantee that `list_transcription_speakers` returns structured Ebby speaker datasets. If the Ebby API returns a speaker object with missing fields, your Pydantic AI agent fails loudly instead of silently corrupting your database. The same strict validation applies when calling `get_transcription_details` to check Ebby processing settings. This prevents your Pydantic AI workflows from acting on incomplete or malformed Ebby configuration data.

Safely extract parsed transcription text

Your Pydantic AI agent invokes `get_transcription_text` to extract raw Ebby text content from completed files. The Pydantic AI framework validates the text payload structure, ensuring your downstream models receive clean, typed strings. To keep track of recent Ebby updates, the Pydantic AI agent calls `list_latest_transcriptions` to fetch the newest files. This lets your Pydantic AI agent run continuous validation checks on your active Ebby audio pipeline without manual schema mapping.

Setup guide

Set up Ebby MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "ebby-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Ebby tools.",
)

result = await agent.run("List recent Ebby transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Ebby. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Ebby now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Ebby MCP in Pydantic AI

Use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint, and pass it to the `toolsets` argument of your Pydantic AI `Agent`. Do not use the deprecated `MCPServerHTTP` class when configuring Ebby.

Yes, your Pydantic AI agent calls `list_in_progress_transcriptions` to monitor the queue. The Pydantic AI framework validates the status fields against your models, ensuring your loop only proceeds when the Ebby data is clean.

This MCP Server guarantees structured JSON outputs for tools like `quick_transcription_volume_audit`. This allows your Pydantic AI agent to parse Ebby usage rates and activity volume without writing custom parser code.

Have your Pydantic AI agent call `list_successfully_processed_audio` to find files ready for export. The returned list of Ebby files is parsed directly into typed Python objects for safe Pydantic AI downstream processing.

All Ebby transcription text and speaker data are processed through isolated, ephemeral V8 sandboxes. Your Pydantic AI agent connects over an encrypted SSE or HTTP transport, ensuring no Ebby data is logged or cached on Vinkius.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript